Generalization of Dynamic Two Stage Models in DEA: An Application in Saderat Bank

Document Type: Full Length Article

Authors

1 Department of Mathematics, Central Tehran Branch, Islamic Azad University, Tehran, Iran.

2 Department of Mathematics, Islamic Azad University, Central Tehran Branch, Iran.

Abstract

Dynamic network data envelopment analysis (DNDEA) has attracted a lot of attention in recent years. On one hand the available models in DNDEA evaluating the performance of a DMU with interrelated processes during specified multiple periods but on the other hand they can only measure the efficiency of dynamic network structure when a supply chain structure present. For example, in the banking industry, profit is generated by using loan as a source of investment funds, and the generate profit can also be regarded as an added source. Existing models are not able to use output from different section in different period as inputs, for the next section. So we propose a dynamic network DEA model involve two-stage structure in each period. Hence, this article is composite of two-stage and dynamic DEA that is called dynamic two-stage DEA (DTDEA) model. IT has the advantages of both dynamic DEA and two-stage models. This model can be utilized to highlight those bank branch managers can be further analyzed for best practice benchmarking. A set of bank branches is used to illustrate how the new model can be utilized to characterize the direct impact of profit on branches performance. The real data is extracted from monthly released financial data of the 94 Saderat Bank branches through 1395.

Keywords